open-llm-leaderboard-old/details_cognitivecomputations__fc-dolphin-2.6-mistral-7b-dpo-laser
收藏数据集概述
数据集简介
该数据集是在评估模型 cognitivecomputations/fc-dolphin-2.6-mistral-7b-dpo-laser 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含63个配置，每个配置对应一个评估任务。
数据集结构
数据集由1次运行创建，每个运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
数据加载示例
以下是加载数据集的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_cognitivecomputations__fc-dolphin-2.6-mistral-7b-dpo-laser", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-21T18:23:59.965478 运行 的最新结果：
python { "all": { "acc": 0.6354430677525905, "acc_stderr": 0.03236012383081897, "acc_norm": 0.6398936931215545, "acc_norm_stderr": 0.03300836569572193, "mc1": 0.412484700122399, "mc1_stderr": 0.01723329939957122, "mc2": 0.5774896416761253, "mc2_stderr": 0.015809498057048683 }, "harness|arc:challenge|25": { "acc": 0.6083617747440273, "acc_stderr": 0.014264122124938215, "acc_norm": 0.6296928327645052, "acc_norm_stderr": 0.01411129875167495 }, "harness|hellaswag|10": { "acc": 0.6547500497908784, "acc_stderr": 0.004744780201276635, "acc_norm": 0.8417645887273452, "acc_norm_stderr": 0.003642157166162346 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411021, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411021 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6518518518518519, "acc_stderr": 0.041153246103369526, "acc_norm": 0.6518518518518519, "acc_norm_stderr": 0.041153246103369526 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6513157894736842, "acc_stderr": 0.0387813988879761, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.0387813988879761 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.028254200344438662, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.028254200344438662 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.049999999999999996, "acc_norm": 0.45, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.45098039215686275, "acc_stderr": 0.04951218252396264, "acc_norm": 0.45098039215686275, "acc_norm_stderr": 0.04951218252396264 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5148936170212766, "acc_stderr": 0.03267151848924777, "acc_norm": 0.5148936170212766, "acc_norm_stderr": 0.03267151848924777 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.041227371113703316, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.041227371113703316 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3968253968253968, "acc_stderr": 0.025197101074246487, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.025197101074246487 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7580645161290323, "acc_stderr": 0.024362599693031086, "acc_norm": 0.7580645161290323, "acc_norm_stderr": 0.024362599693031086 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7777777777777778, "acc_stderr": 0.029620227874790486, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.029620227874790486 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8860103626943006, "acc_stderr": 0.022935144053919436, "acc_norm": 0.8860103626943006, "acc_norm_stderr": 0.022935144053919436 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6461538461538462, "acc_stderr": 0.024243783994062157, "acc_norm": 0.6461538461538462, "acc_norm_stderr": 0.024243783994062157 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948485, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.028742040903948485 }, "harness|hendrycksTest-high_
